| Mataric, M.J.: Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In Dautenhahn, K., Nehaniv, C., eds.: Imitation in Animals and Artifacts. MIT Press (2002) |
....when an action was performed by a subject or when another individual was perceived performing the same action. In addition, imitation has also been suggested as a possible basis for language learning [164] These results have spurred applied efforts in imitative approaches to robotics by Mataric [123], Brooks [31] etc. where imitation has gained visibility and complemented reinforcement learning [107] Further arguments for imitation based learning include improved acquisition of complex visual gestures in human subjects [39] However, these domains have predominantly focused on uncovering ....
.... and complemented reinforcement learning [107] Further arguments for imitation based learning include improved acquisition of complex visual gestures in human subjects [39] However, these domains have predominantly focused on uncovering direct mappings between action and perception [169] [123]. It is through such a mapping that the imitation learning problem can be translated into a direct supervised learning one. This complex mapping is to a certain extent the Achilles heel of imitation learning. Much of the effort of humanoid robot imitation rests in resolving Meltzoff and Moore s ....
M.J. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In C. Nehaniv and K. Dautenhahn, editors, Imitation in Animals and Artifacts. MIT Press, 1999.
....discretization becomes infeasible when the state space is highly dimensional. Action based discretization becomes infeasible when there are too many degrees of freedom. Interestingly, biological high degree of freedom systems are often governed by a much smaller collection of motor primitives [3]. We focus here on action based discretization. Action based discretization consists of two parts: 1) action parameter discretization and (2) action timing discretization, i.e. how and when to act. For example, consider robot soccer. Search can only sample action parameter continua such as kick ....
Maja J. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In C. Nehaniv and K. Dautenhahn, editors, Imitation in Animals and Artifacts, Cambridge, MA, USA, 2000. MIT Press. See also USC technical report IRIS99 -377.
No context found.
M. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In K. Dautenhaun and C. Nehaniv, editors, Imitation in Animals and Artifiacts, pages 391--422. MIT Press, 2000.
No context found.
M. J. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In C. Nehaniv & K. Dautenhahn, editor, Imitation in Animals and Artifacts. The MIT Press, 2000.
No context found.
M. Mataric, "Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics," in Imitation in Animals and Artifiacts, K. Dautenhaun and C. Nehaniv, Eds. MIT Press, 2002, pp. 391--422.
No context found.
M. J. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In C. Nehaniv and K. Dautenhahn, editors, Imitation in Animals and Artifacts. MIT Press, Cambridge, to appear, 2001.
....enables a robot to greatly reduce the space of possible trajectories to a subset that approximates that of the observed demonstration. Refinement through trial and error is still likely to be required, but in a greatly reduced learning space. We have developed a model for learning by imitation [16, 23, 19], inspired by two lines of neuroscience evidence: motor primitives [5] and mirror neurons [14] Motor primitives are biological structures that organize the underlying mechanisms of complete movements, including spinal fields [5] and central pattern generators [32] In a computational sense, ....
....and motor routines. This mapping process also serves as a substrate for more complex and less direct forms of skill acquisition. In this view, primitives are the fundamental building blocks of motor control, which impose a bias on movement perception and facilitate its execution, i.e. imitation [19]. Determining an effective basis set of primitives is thus a difficult problem. Our previous work has explored hand coded primitives [22, 16] Here, we describe a method for automatically generating a set of arm movement primitives from human movement data. We hypothesize that the trajectory ....
[Article contains additional citation context not shown here]
M. J. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics (in press). In C. Nehaniv & K. Dautenhahn, editor, Imitation in Animals and Artifacts. The MIT Press, 2001.
....for a system in which a 7 DOF robot arm learned the task of balancing a pole from a brief human demonstration. Other work in our lab is also exploring imitation based on mapping observed human demonstration onto a set of behavior primitives, implemented on a 20 DOF dynamic humanoid simulation [16, 11]. The key difference between the work presented here and those above is at the level of learning. The work above focuses on learning at the level of action imitation (and thus usually results in acquiring reactive policies) while our approach enables learning of high level, sequential tasks. 6. ....
M. J. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In C. Nehaniv and K. Dautenhahn, editors, Imitation in Animals and Artifacts. MIT Press, Cambridge, to appear, 2001.
....body of 3 research in robotics, and contribute to data segmentation and understanding. However, they provide highly task specific solutions, with little flexibility for applying the same algorithm to imitation after different types of movements and tasks. More recent efforts, including our own [3, 8, 10, 37], have been oriented toward analyzing the underlying mechanisms of imitation in natural systems and modeling those on artificial ones. Atkeson and Schaal [5, 49] developed a control strategy in which the robot learns a reward function from the demonstration and a task model from repeated attempts ....
M. J Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In Chrystopher Nehaniv and Kerstin Dautenhahn, editors, Imitation in Animals and Artifacts. The MIT Press, 2001 (In Press). 21
....for a system in which a 7 DOF robot arm learned the task of balancing a pole from a brief human demonstration. Other work in our lab is also exploring imitation based on mapping observed human demonstration onto a set of behavior primitives, implemented on a 20 DOF dynamic humanoid simulation [28], 29] The key di erence between the work presented here and those above is at the level of learning. The work above focuses on learning at the level of action imitation (and thus usually results in acquiring reactive policies) while we are concerned with learning high level, sequential tasks. ....
Maja J Mataric, \Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics," in Imitation in Animals and Artifacts, Chrystopher Nehaniv and Kerstin Dautenhahn, Eds. MIT, to appear, 2001.
.... behavior as well as to learn arbitrary new skills, i.e. skills that are irrelevant to the goal, by observation [2] So called true imitation is thought to be a complex mechanism, since it is found in very few species, while mimicry is more common [17] We have proposed a model of imitation [14, 9] based on evolutionarily older substrates including motor primitives as the basis for motor control and the mirror system [8, 19, 20] as the basis for a direct sensorymotor mapping for mimicry. Our other work [14, 9, 4, 23, 1] is aimed at developing and implementing this model on a variety of ....
....species, while mimicry is more common [17] We have proposed a model of imitation [14, 9] based on evolutionarily older substrates including motor primitives as the basis for motor control and the mirror system [8, 19, 20] as the basis for a direct sensorymotor mapping for mimicry. Our other work [14, 9, 4, 23, 1] is aimed at developing and implementing this model on a variety of synthetic humanoid platforms, in order to validate the model on real world tasks. In this paper, we focus on a set of psychophysical imitation experiments we performed in order to gain further insight and constraints for our ....
[Article contains additional citation context not shown here]
Mataric, M.J.: Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics, in C. Nehaniv & K. Dautenhahn, eds, `Imitation in Animals and Artifacts', The MIT Press, 2000.
....couples the observation of certain movements and their motor execution [32] Our primitives serve an analogous function, being a basis set for structuring motor control and a vocabulary for classifying and imitating observed movements. We describe a model of imitation based on such primitives [25]. Next, we demonstrate the feasibility of the model in a constrained implementation. We present approximate motion reconstruction generated from visually captured data of typically imitated tasks taken from aerobics, dancing, and athletics. The rest of the paper is organized as follows. In ....
....or learned, as in our other work [14] Complex motor behaviors result from sequences and or superpositions of the primitives. Our model is based on neurosceince evidence for motor primitives , which structure movement, and mirror neurons, which couple such movement with associated visual inputs [25], discussed in more detail below. We developed the notion of perceptuo motor primitives as the unifying mechanism between the perceptual and motor systems, influenced by the constraints of each. These primitives encode generic movements, invariant to exact Cartesian position, rate of motion, ....
[Article contains additional citation context not shown here]
Maja J Mataric. Sensory-motor primitives as a basis for imitation: Linking perc eption to action and biology to robotics. In Imitation in Animals and Artifacts. The MIT Press, 2000.
No context found.
M.J. Mataric , "Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics, Imitation in
....solutions, with little flexibility for applying the same algorithm to imitation after types of movements and tasks. More recent efforts, including our own, have been oriented toward analyzing the underlying mechanisms of imitation in natural systems and modeling those on artificial ones [4, 6, 5, 9, 10, 31, 42, 41]. The endeavor, there, is, on the one hand, to build biologically plausible models of animal s imitative abilities, and, on the other hand, to develop architecture for visuo motor control and learning in robots which would show some of the flexibility of natural systems. 2 Our work wishes to ....
M. J Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In Chrystopher Nehaniv and Kerstin Dautenhahn, editors, Imitation in Animals and Artifacts. The MIT Press, 2000.
No context found.
Mataric, M.J.: Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In Dautenhahn, K., Nehaniv, C., eds.: Imitation in Animals and Artifacts. MIT Press (2002)
No context found.
M. J. Mataric, Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics, in C. L. Nehaniv and K. Dautenhahn (Eds.) Imitation in Animals and Artefacts (Cambridge, MA: The MIT Press, 2002) 392-422.
No context found.
. M.J. Mataric, Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics, Imitation in Animals and Artefacts, Eds. C. L. Nehaniv and K. Dautenhahn, Cambridge, MA: The MIT Press, 2002, pages 392-422.
No context found.
Mataric M. 2002. `Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics'. In Nehaniv CL, Dautenhahn K., Imitation in Animals and Artefacts, Cambridge, MA: The MIT Press, p. 391--422.
No context found.
M. J. Mataric, "Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics," in Imitation in Animals and Artefacts, C. L. Nehaniv and K. Dautenhahn Eds. Cambridge, MA: The MIT Press, pp. 392-422, 2002.
No context found.
M. J. Mataric, "Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics," in Imitation in Animals and Artefacts, C. L. Nehaniv and K. Dautenhahn Eds. Cambridge, MA: The MIT Press, pp. 392-422, 2002.
No context found.
M. J. Mataric. Sensory-motor primitives as a basis for imitation: linking perception to action and biology to robotics. C. Nehaniv & K. Dautenhahn (Eds.), Imitation in animals and artifacts, MIT Press, 2001
No context found.
Maja J. Matari c. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In C. Nehaniv and K. Dautenhahn, editors, Imitation in Animals and Artifacts. MIT Press, 2000.
No context found.
M. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In C. Nehaniv and K. Dautenhahn, editors, Imitation in Animals and Artifacts. MIT Press, 1999.
No context found.
M. J. Mataric. Sensory-motor primitives as a basis for imitation: linking perception to action and biology to robotics. In C. Nehaniv and K. Dautenhahn, editors, Imitation in Animals and Artifacts. The MIT Press, Cambridge, MA, 2000.
No context found.
M.J. Mataric. Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In C. Nehaniv and K. Dautenhahn, editors, Imitation in Animals and Artifacts. MIT Press, 1999.
First 50 documents
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC